© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 91739
    Prev
    Next
    INDEX
    Explanations

    references to clichés and repetitive phrases

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    lier
    -0.07
    /downloads
    -0.07
    uge
    -0.06
    anford
    -0.06
    ัà¹Ī
    -0.06
    sel
    -0.06
    liers
    -0.06
    êt
    -0.06
     akt
    -0.06
    èĢ
    -0.06
    POSITIVE LOGITS
     clich
    0.07
    ÅĻi
    0.07
    oti
    0.07
    ishly
    0.06
     trop
    0.06
    sterol
    0.06
     stere
    0.06
    à¸Ľà¸£à¸°à¸Īำ
    0.06
     shm
    0.06
     excuses
    0.06
    Activations Density 0.009%

    No Known Activations